Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Social Motion Prediction with Cognitive Hierarchies
Wentao Zhu, Jason Qin, Yuke Lou, Hang Ye, Xiaoxuan Ma, Hai Ci, Yizhou Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| introduce recursive cognitive reasoning (K=3 rather than K=0) (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | global pose error: 163.7 -> 152.5 | Improved |
| introduce recursive cognitive reasoning (K=3 rather than K=0) (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | root position error: 131.8 -> 124.0 | Improved |
| increase reasoning depth from K=1 to K=3 (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | global pose error: 155.5 -> 152.5 | Improved |
| increase reasoning depth from K=2 to K=3 (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | global pose error: 154.2 -> 152.5 | Improved |
| increase reasoning depth from K=3 to K=4 (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | global pose error: 152.5 -> 153.5 | No clear effect |
| add GAIL regularization at intermediate levels (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | root position error: 126.9 -> 124.0 | Improved |
| add GAIL regularization (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | root position error: 127.0 -> 124.0 | Improved |
| add GAIL regularization (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | local pose error: 86.8 -> 86.6 | Hurt |
| share policy network weights across reasoning levels (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | global pose error: 160.2 -> 152.5 | Improved |
| share policy network weights across reasoning levels (ablation) | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | root position error: 129.5 -> 124.0 | Improved |
| use the proposed method instead of SoMoFormer | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | global pose error: 160.0 -> 152.5 | Improved |
| use the proposed method instead of HRI | Social Motion Prediction with Cognitive Hierarchies · Wusi, 1000ms | local pose error: 94.1 -> 86.6 | Improved |
Closest papers by meaning
- FlowMoP: Stochastic Multi-Person Motion Prediction (NeurIPS 2026 · similarity 0.88)
- Social Diffusion: Long-term Multiple Human Motion Anticipation (ICCV 2023 · similarity 0.87)
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations (CVPR 2024 · similarity 0.85)
- Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning (CVPR 2024 · similarity 0.85)
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.85)
- SimpliHuMoN: Simplifying Human Motion Prediction (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
